MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition
arXiv:2102.12664
Abstract
In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features (e.g., mel-spectrograms or MFCC) as the input, and recognizing both text sequences, where the two recognition losses use the same combination weight. We apply MixSpeech on two popular end-to-end speech recognition models including LAS (Listen, Attend and Spell) and Transformer, and conduct experiments on several low-resource datasets including TIMIT, WSJ, and HKUST. Experimental results show that MixSpeech achieves better accuracy than the baseline models without data augmentation, and outperforms a strong data augmentation method SpecAugment on these recognition tasks. Specifically, MixSpeech outperforms SpecAugment with a relative PER improvement of 10.6 on TIMIT dataset, and achieves a strong WER of 4.7 on WSJ dataset.
To appear at ICASSP 2021
References in corpus (6)
- mixup: Beyond Empirical Risk Minimization
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Transformers with convolutional context for ASR
- Augmenting Data with Mixup for Sentence Classification: An Empirical Study
- Almost Unsupervised Text to Speech and Automatic Speech Recognition
- Semantic Mask for Transformer based End-to-End Speech Recognition